Using sensor data for coordinate prediction

Abstract

Systems and methods of using sensor data for coordinate prediction are disclosed herein. In some example embodiments, for a place, a computer system accesses corresponding service data comprising pick-up data and drop-off data for requests, and accesses corresponding sensor data indicating at least one path of mobile devices of the requesters of the requests, with the at least one path comprising at least one of a pick-up path ending at the pick-up location indicated by the pick-up data and a drop-off path beginning at the drop-off location indicated by the drop-off data. In some example embodiments, the computer system generates at least one predicted geographic location using the paths indicated by the sensor data, and stores the at least one predicted geographic location in a database in association with an identification of the place.

What is claimed is: 
     
       1. A computer-implemented method comprising:
 accessing, by a computer system having at least one hardware processor, corresponding sensor data for each one of a plurality of requests for a transportation service comprising delivery of an item to or from a place, the corresponding sensor data indicating at least one path of a mobile device of a provider of the transportation service corresponding to the one of the plurality of requests, the at least one path having been walked by the provider before entering or after exiting a vehicle used by the provider to provide the transportation service; 
 generating, by the computer system, at least one predicted geographic location using the paths indicated by the sensor data of the plurality of requests; and 
 storing, by the computer system, the at least one predicted geographic location in a database in association with an identification of the place. 
 
     
     
       2. The computer-implemented method of  claim 1 , wherein the at least one path comprises a pick-up path ending at a pick-up location where the delivery of the item began. 
     
     
       3. The computer-implemented method of  claim 2 , wherein the pick-up location is determined based on a selection of a selectable user interface element displayed on the mobile device of the provider. 
     
     
       4. The computer-implemented method of  claim 1 , wherein the at least one path comprises a drop-off path beginning at a drop-off location where the delivery of the item ended. 
     
     
       5. The computer-implemented method of  claim 4 , wherein the drop-off location is determined based on a selection of a selectable user interface element displayed on the mobile device of the provider. 
     
     
       6. The computer-implemented method of  claim 1 , further comprising:
 receiving, by the computer system, a request for the transportation service associated with the place from a computing device of a requester, the other request comprising the identification of the place; 
 identifying, by the computer system, at least one of the at least one predicted geographical location of the place based on a search of the database using the identification of the place; and 
 transmitting, by the computer system, the at least one of the at least one predicted geographical location of the place to a computing device of another provider of the transportation service of the request. 
 
     
     
       7. The computer-implemented method of  claim 1 , wherein:
 the corresponding sensor data for each one of the plurality of requests comprises a plurality of geocodes forming the corresponding at least one path indicated by the sensor data; and 
 the generating the at least one predicted geographic location comprising applying at least one clustering algorithm on the paths indicated by the sensor data of the plurality of requests. 
 
     
     
       8. The computer-implemented method of  claim 7 , wherein the generating the at least one predicted geographic location further comprises:
 determining a point of peak concentration from among the paths indicated by the sensor data of the plurality of requests based on the application of the at least one clustering algorithm on the paths indicated by the sensor data of the plurality of requests; and 
 generating the at least one predicted geographic location based on the point of peak concentration. 
 
     
     
       9. The computer-implemented method of  claim 1 , wherein the at least one predicted geographical location of the place corresponds to a point of intersection among a plurality of the paths indicated by the sensor data of the plurality of requests. 
     
     
       10. The computer-implemented method of  claim 1 , wherein the use of the paths in generating the at least one predicted geographical location is based on a determination that an amount of the service data for the place satisfies a minimum threshold amount. 
     
     
       11. The computer-implemented method of  claim 1 , wherein the generating the at least one predicted geographic location also uses boundary data of the place, the boundary data comprising at least one of map data of the place, global positioning system (GPS) data of the mobile device of a requester, Wi-Fi data of the mobile device of the requester, and architectural data of the place. 
     
     
       12. The computer-implemented method of  claim 11 , wherein the generating the at least one predicted geographic location comprises:
 for each one of the plurality of requests, identifying a portion of the at least one path indicated by the corresponding sensor data that is within a boundary of the place based on the boundary data of the place; 
 for each one of the plurality of requests, trimming the identified portion of the at least one path indicated by the corresponding sensor data to form a trimmed version of the at least one path that excludes the identified portion; and 
 generating the at least one predicted geographic location using the trimmed versions of the paths indicated by the sensor data of the plurality of requests. 
 
     
     
       13. The computer-implemented method of  claim 11 , wherein the boundary data comprises at least one of the GPS data of the mobile device of a requester and the Wi-Fi data of the mobile device of the requester, the GPS data indicating a GPS signal strength, and the Wi-Fi data indicating a Wi-Fi signal strength. 
     
     
       14. A system comprising:
 at least one hardware processor; and 
 a non-transitory machine-readable medium embodying a set of instructions that, when executed by the at least one hardware processor, cause the at least one hardware processor to perform operations, the operations comprising: 
 accessing corresponding sensor data for each one of a plurality of requests for a transportation service comprising delivery of an item to or from a place, the corresponding sensor data indicating at least one path of a mobile device of a provider of the transportation service corresponding to the one of the plurality of requests, the at least one path having been walked by the provider before entering or after exiting a vehicle used by the provider to provide the transportation service; 
 generating at least one predicted geographic location using the paths indicated by the sensor data of the plurality of requests; and 
 storing the at least one predicted geographic location in a database in association with an identification of the place. 
 
     
     
       15. The system of  claim 14 , wherein the at least one path comprises a pick-up path ending at a pick-up location where the delivery of the item began. 
     
     
       16. The system of  claim 15 , wherein the pick-up location is determined based on a selection of a selectable user interface element displayed on the mobile device of the provider. 
     
     
       17. The system of  claim 14 , wherein the at least one path comprises a drop-off path beginning at a drop-off location where the delivery of the item ended. 
     
     
       18. The system of  claim 17 , wherein the drop-off location is determined based on a selection of a selectable user interface element displayed on the mobile device of the provider. 
     
     
       19. The system of  claim 14 , wherein the operations further comprise:
 receiving a request for the transportation service associated with the place from a computing device of a requester, the request comprising the identification of the place; 
 identifying at least one of the at least one predicted geographical location of the place based on a search of the database using the identification of the place; and 
 transmitting the at least one of the at least one predicted geographical location of the place to a computing device of another provider of the transportation service of the other request. 
 
     
     
       20. A non-transitory machine-readable medium embodying a set of instructions that, when executed by at least one hardware processor, cause the at least one hardware processor to perform operations, the operations comprising:
 accessing corresponding sensor data for each one of a plurality of requests for a transportation service comprising delivery of an item to or from a place, the corresponding sensor data indicating at least one path of a mobile device of a provider of the transportation service corresponding to the one of the plurality of requests, the at least one path having been walked by the provider before entering or after exiting a vehicle used by the provider to provide the transportation service; 
 generating at least one predicted geographic location using the paths indicated by the sensor data of the plurality of requests; and 
 storing the at least one predicted geographic location in a database in association with an identification of the place.